© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107492
    Prev
    Next
    INDEX
    Explanations

    row of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    1.73
    s
    1.54
    c
    1.27
    f
    1.23
    d
    1.15
    ದ
    1.05
    j
    1.02
    ম
    1.00
    sá
    0.98
    b
    0.98
    POSITIVE LOGITS
    -
    0.92
    ۰
    0.89
    0
    0.84
    </strong>
    0.80
    ছিল
    0.79
     н
    0.79
    好吃
    0.79
     I
    0.78
     ल
    0.78
     trato
    0.77
    Activations Density 0.001%

    No Known Activations